Kimi K3
inferris/kimi-k3 · family kimi-k3 · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$3.60
Blended $/1M (3:1)
$1.8
Input $/1M
$9
Output $/1M
$10.80
1M in + 1M out
$0.18 −90%
Cache read $/1M
#7419 of 9,563
Cheapest rank
- Provider
- Inferris (
inferris) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 262,144 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“Kimi K3” is offered by 20 providers — cheapest-effective first. SCNet Token Plan is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| SCNet Token Plan | free | free | $0.00 | 1M |
| Nvidia | free | free | $0.00 | 1M |
| SenseNova (China) | free | free | $0.00 | 1M |
| Volcengine Ark Coding Plan | free | free | $0.00 | 1M |
| Kimi For Coding (kimi.com) | free | free | $0.00 | 1M |
| Kimi For Coding (kimi.ai) | free | free | $0.00 | 1M |
| UberLLM | $0.0115 | $0.96 | $0.25 | 1M |
| OpenCheap | $0.15 | $1.2 | $0.41 | 1M |
| UplinkSwitch | $0.9 | $4.5 | $1.80 | 1M |
| NanoGPT | $0.45 | $9.6 | $2.74 | 1M |
| Kenari | $0.8571 | $8.57 | $2.79 | 1M |
| KoRouter | $1.74 | $8.7 | $3.48 | 1M |
| Inferris (this) | $1.8 | $9 | $3.60 | 262k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Inferris and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"kimi-k3","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):